© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 59865
    Prev
    Next
    INDEX
    Explanations

    is likely to be

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    攫
    -1.56
     they
    -1.52
     is
    -1.50
     would
    -1.48
     which
    -1.45
    (!__
    -1.45
     have
    -1.38
    尤其是
    -1.35
    迄
    -1.30
     According
    -1.30
    POSITIVE LOGITS
     the
    2.00
     流れ
    1.52
     some
    1.51
     pueden
    1.49
     estrategias
    1.43
     lác
    1.42
     hermosas
    1.41
     baterie
    1.38
    龇
    1.38
     mogli
    1.34
    Activations Density 0.123%

    No Known Activations